Model comparison
Mistral Nemo vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 26.4 on the Noometry Index. Mistral Nemo costs 9.0× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Mistral Nemo scores higher in 0 categories and Qwen3.5 397B-A17B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 12.3.
- The biggest single-benchmark swing is GPQA Diamond: 29.9% for Mistral Nemo and 86.4% for Qwen3.5 397B-A17B.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 128K.
Side by side
| Mistral Nemo | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.4 | 46.0 |
| Released | 2024-07-01 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.15 | $0.60 |
| Output $ / M tokens | $0.15 | $3.60 |
| Results tracked | 10 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | — | 1400 |
| LMArena Coding | — | 1465 |
Agentic & Tool Use Qwen3.5 397B-A17B leads
Mistral Nemo: 23.5 (#125), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| Berkeley Function Calling Leaderboard | 27.6% | — |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| BALROG | 17.6% | — |
Reasoning Qwen3.5 397B-A17B leads
Mistral Nemo: 20.7 (#232), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| DTBench | 48.6% | 87.5% |
| Epoch Capabilities Index | 118.68 | 146.65 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 18% |
| LMCA | — | 37.9% |
| PIQA | 83.5% | — |
Math Qwen3.5 397B-A17B leads
Mistral Nemo: 25.5 (#268), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LMArena Math | — | 1454 |
| MATH Level 5 | 10.8% | — |
| GSM8K | 84.2% | — |
Knowledge Qwen3.5 397B-A17B leads
Mistral Nemo: 12.3 (#298), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 29.9% | 86.4% |
| LMArena Expert | — | 1462 |
| BoolQ | 82.5% | — |
Multimodal Not comparable
Mistral Nemo: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Not comparable
Mistral Nemo: —, Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1500 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1441 |
Instruction Following Not comparable
Mistral Nemo: —, Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | — | 1424 |
Long Context Not comparable
Mistral Nemo: —, Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Mistral Nemo: 28.5 (#296), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Mistral Nemo | Qwen3.5 397B-A17B |
|---|---|---|
| EQ-Bench Creative Writing | 881 | 1478 |
| LMArena Text | — | 1438 |
| LMArena Creative Writing | — | 1401 |
| LMArena Multi-Turn | — | 1446 |
Frequently asked questions
Is Mistral Nemo better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 26.4 on the Noometry Index. Mistral Nemo costs 9.0× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Mistral Nemo or Qwen3.5 397B-A17B?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 128K.
How many benchmarks do Mistral Nemo and Qwen3.5 397B-A17B share?
4 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen3.5 397B-A17B has 36.